About the job
Waymo is at the forefront of autonomous driving technology, striving to become the world’s most reliable driver. Originating from the Google Self-Driving Car Project in 2009, Waymo has dedicated itself to developing the Waymo Driver—The World’s Most Experienced Driver™—to enhance mobility access and prevent countless lives lost to traffic accidents. Our cutting-edge Waymo Driver is the backbone of our fully autonomous ride-hailing service and can be implemented across various vehicle platforms and applications. Having completed over ten million rider-only trips, our technology has accumulated experience from autonomously driving over 100 million miles on public roads and tens of billions of miles in simulations across more than 15 U.S. states.
The Large Model Evaluation team is pivotal to Waymo's AI mission. As advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) continue, we are constructing state-of-the-art AI systems capable of addressing the full spectrum of real-world driving complexities. Central to our success is our capacity to measure progress effectively. Robust evaluation is crucial for deploying any large model, and at Waymo, the challenge is particularly intricate and safety-critical. We seek quantitatively-minded engineers to innovate and propose new methods for assessing the machine learning models integrated into the Waymo Driver.